Approximate dynamic programming with affine ADDs

The Affine ADD (AADD) is an extension of the Algebraic Decision Diagram (ADD) that compactly represents context-specific, additive and multiplicative structure in functions from a discrete domain to a real-valued range. In this paper, we introduce a novel algorithm for efficiently finding AADD approximations that we use to develop the MADCAP algorithm for AADD-based structured approximate dynamic programming (ADP) with factored MDPs. MADCAP requires less time and space to achieve comparable or better approximate solutions than the current state-of-the-art ADDbased ADP algorithm of APRICODD and can provide approximate solutions for problems with context-specific, additive and multiplicative structure on which APRICODD runs out of memory. Categories and Subject Descriptors I.2.8 [Problem Solving, Control Methods, and Search]: Dynamic programming; Plan execution, formation, and generation General Terms Algorithms Keywords Planning, Markov Decision Processes, Approximate Dynamic Programmi...

• Type: Journal
• Year: 2010
• Where: ATAL
• Authors: Scott Sanner, William T. B. Uther, Karina Valdivia Delgado
• Keywords: Approximate Dynamic Programming, Approximate Solutions, ATAL 2010, Intelligent Agents, Multiplicative Structure